Learning of probabilistic transition models for robotic actions via templates
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis |
Language: | eng |
Published: |
Massachusetts Institute of Technology
2019
|
Subjects: | |
Online Access: | https://hdl.handle.net/1721.1/121497 |
_version_ | 1811091069430923264 |
---|---|
author | Xia, Victoria(Victoria F.) |
author2 | Leslie Pack Kaelbling. |
author_facet | Leslie Pack Kaelbling. Xia, Victoria(Victoria F.) |
author_sort | Xia, Victoria(Victoria F.) |
collection | MIT |
description | This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. |
first_indexed | 2024-09-23T14:56:30Z |
format | Thesis |
id | mit-1721.1/121497 |
institution | Massachusetts Institute of Technology |
language | eng |
last_indexed | 2024-09-23T14:56:30Z |
publishDate | 2019 |
publisher | Massachusetts Institute of Technology |
record_format | dspace |
spelling | mit-1721.1/1214972019-07-06T03:01:05Z Learning of probabilistic transition models for robotic actions via templates Xia, Victoria(Victoria F.) Leslie Pack Kaelbling. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Electrical Engineering and Computer Science. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018 Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 71-72). In this work we present templates as an approach for learning probabilistic transition models for actions. By constructing templates via a greedy procedure for building up lists of deictic references that select relevant objects to pass to a predictor, we learn compact representations for a transition model whose training time and performance do not suffer from the presence of additional objects in more complex scenes. We present various algorithms for simultaneously separating training data into corresponding templates and learning template parameters, through the use of clustering-based approaches for initial assignment of samples to templates, followed by EM-like methods to further separate the data and train templates. We evaluate templates on variants of a simulated, 3D table-top pushing task involving stacks of objects. In comparing our approach to a baseline that considers all objects in the scene, we find that the templates approach is more data-efficient in terms of impact of number of training samples on performance. by Victoria Xia. M. Eng. M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 2019-07-05T17:18:42Z 2019-07-05T17:18:42Z 2018 2018 Thesis https://hdl.handle.net/1721.1/121497 1098214664 eng MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 72 pages application/pdf Massachusetts Institute of Technology |
spellingShingle | Electrical Engineering and Computer Science. Xia, Victoria(Victoria F.) Learning of probabilistic transition models for robotic actions via templates |
title | Learning of probabilistic transition models for robotic actions via templates |
title_full | Learning of probabilistic transition models for robotic actions via templates |
title_fullStr | Learning of probabilistic transition models for robotic actions via templates |
title_full_unstemmed | Learning of probabilistic transition models for robotic actions via templates |
title_short | Learning of probabilistic transition models for robotic actions via templates |
title_sort | learning of probabilistic transition models for robotic actions via templates |
topic | Electrical Engineering and Computer Science. |
url | https://hdl.handle.net/1721.1/121497 |
work_keys_str_mv | AT xiavictoriavictoriaf learningofprobabilistictransitionmodelsforroboticactionsviatemplates |